GE

Gemma 4 64E A4B Heretic

GemmaGGUF by mradermacherUpdated 2026-04-19
Download on Hugging Face
Parameters13.8B
Context256K
Layers30
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Gemma 4 64E A4B Heretic needs about 17.8 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 12.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 64E A4B Heretic – 13.8B parameters, 262144 token context

Gemma 4 64E A4B Heretic is a 13.8B parameter model with 262144 token context. It is a mixture of experts with 4 active parameters. The model excels at instruction following and roleplaying but has limited math accuracy.

Good at

  • Instruction following
  • Roleplaying
  • Reasoning

Limits

  • Math accuracy poor
  • No vision support unless paired with SigLIP
  • License not specified

Best for

  • Chatbot roleplay
  • Custom instruction sets
  • Text generation with large context

Who it’s for. Developers building conversational agents that require deep context and roleplay capabilities. The model is suitable for users who can tolerate limited math performance and are comfortable fine‑tuning or adjusting prompts.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 8.6 GB
Too big Get file →
IQ1_S4.6 GB 13.2 GB
Too big Get file →
IQ1_M4.8 GB 13.4 GB
Too big Get file →
IQ2_XXS5.2 GB 13.7 GB
Too big Get file →
IQ2_XS5.5 GB 14.0 GB
Too big Get file →
IQ2_S5.5 GB 14.1 GB
Too big Get file →
IQ2_M5.8 GB 14.3 GB
Too big Get file →
Q2_K_S5.9 GB 14.5 GB
Too big Get file →
Q2_K5.9 GB 14.5 GB
Too big Get file →
IQ3_XXS6.2 GB 14.8 GB
Too big Get file →
IQ3_XS6.5 GB 15.0 GB
Too big Get file →
IQ3_S6.8 GB 15.3 GB
Too big Get file →
Q3_K_S6.8 GB 15.3 GB
Too big Get file →
IQ3_M6.9 GB 15.5 GB
Too big Get file →
Q3_K_M7.4 GB 15.9 GB
Too big Get file →
Q3_K_L7.7 GB 16.2 GB
Too big Get file →
IQ4_XS7.7 GB 16.3 GB
Too big Get file →
IQ4_NL8.0 GB 16.5 GB
Too big Get file →
Q4_08.0 GB 16.6 GB
Too big Get file →
Q4_K_S8.5 GB 17.1 GB
Too big Get file →
Q4_18.8 GB 17.4 GB
Too big Get file →
Q4_K_M9.2 GB 17.8 GB
Too big Get file →
Q5_K_S9.9 GB 18.4 GB
Too big Get file →
Q5_K_M10.5 GB 19.0 GB
Too big Get file →
Q6_K12.3 GB 20.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.64 GB, 13.2 GB memory at 8k). For 12 GB VRAM, IQ2_XS (5.45 GB, 14 GB memory). For 16 GB VRAM, Q4_K_M (9.21 GB, 17.8 GB memory). Estimates are approximate.

What GPU do you need for Gemma 4 64E A4B Heretic?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_M (7.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 20.9 GB in use).

Which Gemma 4 64E A4B Heretic quant should you choose?

Q4_K_M is the usual starting point for Gemma 4 64E A4B Heretic: it balances file size and quality well. Here it is a 9.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters13.8B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymradermacher
FamilyGemma
Downloads (HF)563
Last updated2026-04-19

Frequently asked questions about Gemma 4 64E A4B Heretic

How much VRAM does Gemma 4 64E A4B Heretic need?

About 17.8 GB at Q4_K_M with an 8K context window. That is the 9.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Gemma 4 64E A4B Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 4 64E A4B Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 4.6 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.2 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.5 GB and 19 more.

What context length does Gemma 4 64E A4B Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Gemma 4 64E A4B Heretic GGUF?

The files are on Hugging Face in the mradermacher/Gemma-4-64E-A4B-Heretic-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, use the IQ1_S quant which is 4.64 GB and requires about 13.2 GB memory at 8k context.

Does this model support vision?

It is a vision model only when paired with the SigLIP mmproj; otherwise it is text‑only.

What is the recommended sampler setting?

Top‑P 0.9 with Temp 0.7–0.8 and Repeat Penalty 1.15 to prevent loops.

Other GGUFs of Gemma-4-64E-A4B-Heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →